I do a fun orchestration system for long running loops on exe.dev (small write up docs.coey.dev) and I feel like I have super powers.
Self healing, I try two ways:
1) use a memory tool to store learnings for next iteration (Deja.coey.dev) and have the loop system instructions tell how to use it. One orchestrator, and sequential worker agents who run til their context is full and then hand off to the next run with learnings
2) the agent Shelley on exe can search past convos when promoted too for continuation.
I’ve been doing this with great success just “falling” into the implementation after proper guardrails are placed
I release stuff all the time, so yes I suppose? Not trying to spam but you can find a mix of open source, b2b saas i own, and client saas I manage on my personal website.
Thank you - take each one with a grain of salt, and heavily ask your AI agent (or your brain) to vet everything. I'm honestly newer to open source, I've been lurking at my desk alone for too long
Thanks for testing - i apologize for wasting your time... But I did take a deep look at things and figured out how to make generation of tools more reliable.
If you're still interested, please take another try... I've got more visibility into logs and errors, and it should be much more reliable!
Thanks! It was born from a conversation with a friend who offers Fractional CFO Services.
One of his most repeated tasks is helping clients predict their cash flow...
So, this tool to simplify and automate that process, making it accessible to everyone. Next steps are going to be exploring some revenue opportunities.
Is it? I'm not so familiar with the specifics of bug bounty programs, but it seems like this issue could cause much more than 3k in damages if it were to be exploited.
Similarly, I'm kind of shocked that Google is only offering 30k for discoveries of remote code execution vulnerabilities on their own servers. I don't mean to trivialize that amount of money, but compared to the scope of what that kind of vulnerability could be used for it seems insignificant. There's the potential for access to internal Google secrets and private data belonging to users. Would a government not pay 10-20x for something like that?
No it’s not! That is extremely low compared to say Apple, which doles out something like 50k for low severity bugs (source: they pretty much paid my college fees)
Launched a bare-bones prototype, Inbox.Dog, aiming to rethink B2B email with a sprinkle of AI—think of it as email, but with an AI-powered twist for tasks we haven't fully imagined yet.
It's rough around the edges (it literally could not be a simpler prototype), but I'm curious about its potential to evolve email beyond its current state.
Keen to explore how AI could make email a more powerful tool?
I'd love to hear your thoughts or see you give it a whirl by emailing hello@inbox.dog
Self healing, I try two ways:
1) use a memory tool to store learnings for next iteration (Deja.coey.dev) and have the loop system instructions tell how to use it. One orchestrator, and sequential worker agents who run til their context is full and then hand off to the next run with learnings
2) the agent Shelley on exe can search past convos when promoted too for continuation.
I’ve been doing this with great success just “falling” into the implementation after proper guardrails are placed
reply